#787 - Move encoder implementation details to external shim library (not dependent on the Spark 4 release) #800
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,67 @@ | ||
| package frameless | ||
|
|
||
| import frameless.TypedEncoder.CollectionConversion | ||
| import org.apache.spark.sql.catalyst.InternalRow | ||
| import org.apache.spark.sql.catalyst.expressions.codegen.{ | ||
| CodegenContext, | ||
| CodegenFallback, | ||
| ExprCode | ||
| } | ||
| import org.apache.spark.sql.catalyst.expressions.{ Expression, UnaryExpression } | ||
| import org.apache.spark.sql.types.{ DataType, ObjectType } | ||
|
|
||
| case class CollectionCaster[F[_], C[_], Y]( | ||
| child: Expression, | ||
| conversion: CollectionConversion[F, C, Y]) | ||
| extends UnaryExpression | ||
| with CodegenFallback { | ||
|
|
||
| protected def withNewChildInternal(newChild: Expression): Expression = | ||
| copy(child = newChild) | ||
|
|
||
| override def eval(input: InternalRow): Any = { | ||
| val o = child.eval(input).asInstanceOf[Object] | ||
| o match { | ||
| case col: F[Y] @unchecked => | ||
| conversion.convert(col) | ||
| case _ => o | ||
| } | ||
| } | ||
|
|
||
| override def dataType: DataType = child.dataType | ||
| } | ||
|
|
||
| case class SeqCaster[C[X] <: Iterable[X], Y](child: Expression) | ||
| extends UnaryExpression { | ||
|
|
||
| protected def withNewChildInternal(newChild: Expression): Expression = | ||
| copy(child = newChild) | ||
|
|
||
| // eval on interpreted works, fallback on codegen does not, e.g. with ColumnTests.asCol and Vectors, the code generated still has child of type Vector but child eval returns X2, which is not good | ||
| override def eval(input: InternalRow): Any = { | ||
| val o = child.eval(input).asInstanceOf[Object] | ||
| o match { | ||
| case col: Set[Y] @unchecked => | ||
| col.toSeq | ||
| case _ => o | ||
| } | ||
| } | ||
|
|
||
| def toSeqOr[T](isSet: => T, or: => T): T = | ||
| child.dataType match { | ||
| case ObjectType(cls) | ||
| if classOf[scala.collection.Set[_]].isAssignableFrom(cls) => | ||
| isSet | ||
| case t => or | ||
| } | ||
|
|
||
| override def dataType: DataType = | ||
| toSeqOr(ObjectType(classOf[scala.collection.Seq[_]]), child.dataType) | ||
|
|
||
| override protected def doGenCode( | ||
| ctx: CodegenContext, | ||
| ev: ExprCode | ||
| ): ExprCode = | ||
| defineCodeGen(ctx, ev, c => toSeqOr(s"$c.toVector()", s"$c")) | ||
|
|
||
| } |
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I wonder, is it how scalafmt formats it?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
the builds won't run unless scalafmt is run on files, so yes, those settings lead to some hideous looking code.